Wu M, Lin S, Xiao C, Xiao X, Xu S, Yu S. The emotion prediction of college students with attention LSTM during the COVID19 epidemic.
Sci Rep 2023;
13:22825. [PMID:
38129509 PMCID:
PMC10739690 DOI:
10.1038/s41598-023-50322-x]
[Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2023] [Accepted: 12/18/2023] [Indexed: 12/23/2023] Open
Abstract
During the COVID19 pandemic, there is a pronounced collective mental health issue among college students. Forecasting the trend of emotional changes in on-campus students is crucial to effectively address this issue. This study proposes an Attention-LSTM neural network model that performs deep learning on key input sequence information, so as to predict the distribution of emotional states in college students. By testing 60 consecutive days of emotional data, the model successfully predicts students' emotional distribution, triggers and resolution strategies, with an accuracy rate of no less than 99%. Compared with models such as ARIMA, SARIMA and VAR, this model shows significant advantages in accuracy, operational efficiency, and data collection requirements. The integration of deep learning technology with student management in this study offers a novel approach to address emotional issues among students under exceptional circumstances.
Collapse